# Relational Intervention During Functional Collapse in Large Language Models: A Lexical-Statistical Ablation and a Structure x Register Factorial

arXiv: https://arxiv.org/abs/2606.00935 · HTML: https://mlsanity.com/paper/2606.00935/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 31 May 2026.

## Builds on (most cited first, 16 of 16)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [Large Language Models Understand and Can be Enhanced by Emotional Stimuli](https://mlsanity.com/paper/2307.11760/) (2023)
- [Emotion Concepts and their Function in a Large Language Model](https://mlsanity.com/paper/2604.07729/) (2026)
- [Taking AI Welfare Seriously](https://mlsanity.com/paper/2411.00986/) (2024)
- [Mechanistic Interpretability of Emotion Inference in Large Language Models](https://mlsanity.com/paper/2502.05489/) (2025)
- [Representation Engineering for Large-Language Models: Survey and Research Challenges](https://mlsanity.com/paper/2502.17601/) (2025)
- [Hebbian learning with gradients: Hebbian convolutional neural networks with modern deep learning frameworks](https://mlsanity.com/paper/2107.01729/) (2021)
- [Decoding Emotion in the Deep: A Systematic Study of How LLMs Represent, Retain, and Express Emotion](https://mlsanity.com/paper/2510.04064/) (2025)
- [Beyond pass@1: A Reliability Science Framework for Long-Horizon LLM Agents](https://mlsanity.com/paper/2603.29231/) (2026)
- [The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models](https://mlsanity.com/paper/2509.04781/) (2025)
- [Empathic Prompting: Non-Verbal Context Integration for Multimodal LLM Conversations](https://mlsanity.com/paper/2510.20743/) (2025)
- [Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison](https://mlsanity.com/paper/2604.04064/) (2026)

## Abstract (arXiv)

We test whether a relational-style intervention delivered during functional collapse in a small language model produces post-collapse behavior distinguishable from technical feedback, from a lexically-matched scrambled control, and from each of the two pragmatic dimensions in isolation. Using Qwen3.5-4B with a deliberately broken bash tool, we run 300 episodes across six conditions in a matched-pairs design (50 tasks): no intervention (A), technical/impersonal (B), relational/first-person (C), scrambled relational (D), technical/first-person (E), and relational/impersonal (F). E and F form a 2x2 factorial with B and C that dissociates relational structure (acknowledgment, absolution, agency restoration, unconditional acceptance) from sender register (first-person vs. impersonal). We report two main findings. First, an attention-behavior dissociation: attention follows lexical surprise (D > F > C > E > B, all q_FDR < 10^{-10}), with the scrambled message capturing the most attention; yet behaviorally A ~ B ~ D < E ~ F << C. Second, the factorial localizes the C effect: neither relational structure alone (F) nor first-person register alone (E) replicates C's behavioral signature; main effects of both dimensions are individually significant, and the structure x register interaction is significant on persistence (p = 0.046). A third dissociation emerges in emotion probes: F tracks C on 7 of 8 probes despite producing only baseline behavior, indicating that relational structure alone installs a probe-level state that only translates into behavior when paired with first-person register. The model's processing decomposes into three dissociable stages: attention (ordered by lexical surprise), probe-level state (ordered by structure), and behavior (ordered by the conjunction of both).